LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Meta Llama 3 8B Instruct FP8 KV by neuralmagic

 »  All LLMs  »  neuralmagic  »  Meta Llama 3 8B Instruct FP8 KV   URL Share it on

  12278   
  Autotrain compatible   Conversational   Endpoints compatible   Fp8   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV 

Meta Llama 3 8B Instruct FP8 KV Benchmarks

LLME Score: 0.23669
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3 8B Instruct FP8 KV (neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV)

Meta Llama 3 8B Instruct FP8 KV Parameters and Internals

Model Type 
quantized
Additional Notes 
Meta-Llama-3-8B-Instruct quantized to FP8 using per-tensor quantization, includes FP8 quantized KV Cache.
LLM NameMeta Llama 3 8B Instruct FP8 KV
Repository 🤗https://huggingface.co/neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV 
Model Size8b
Required VRAM9.1 GB
Updated2025-03-12
Maintainerneuralmagic
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Meta Llama 3 8B Instruct FP8 KV

Model
Likes
Downloads
VRAM
Meta Llama 3 8B Instruct GPTQ326615 GB
Meta Llama 3 8B Instruct GPTQ11385 GB
Meta Llama 3 8B Instruct GPTQ095 GB
Meta Llama 3 8B Instruct 8bit079 GB
...ta Llama 3 8B Instruct GPTQ 8B0239 GB
Meta Llama 3 8B Instruct GGUF11364 GB
Meta Llama 3 8B Instruct 8bit5849 GB
Meta Llama 3 8B Instruct GPTQ0165 GB
Meta Llama 3 8B Instruct GPTQ095 GB

Best Alternatives to Meta Llama 3 8B Instruct FP8 KV

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB5133681
P1024K / 16.1 GB1190
931024K / 16.1 GB840
1171024K / 16.1 GB330
Mpasila Viking 8B1024K / 16.1 GB840
93a1024K / 16.1 GB200
1261024K / 16.1 GB130
1361024K / 16.1 GB130
1331024K / 16.1 GB120
161024K / 16.1 GB1690
Note: green Score (e.g. "73.2") means that the model is better than neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV.

Rank the Meta Llama 3 8B Instruct FP8 KV Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 44902 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer